Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation

12/09/2020
by   Robin Chan, et al.
0

Deep neural networks (DNNs) for the semantic segmentation of images are usually trained to operate on a predefined closed set of object classes. This is in contrast to the "open world" setting where DNNs are envisioned to be deployed to. From a functional safety point of view, the ability to detect so-called "out-of-distribution" (OoD) samples, i.e., objects outside of a DNN's semantic space, is crucial for many applications such as automated driving. A natural baseline approach to OoD detection is to threshold on the pixel-wise softmax entropy. We present a two-step procedure that significantly improves that approach. Firstly, we utilize samples from the COCO dataset as OoD proxy and introduce a second training objective to maximize the softmax entropy on these samples. Starting from pretrained semantic segmentation networks we re-train a number of DNNs on different in-distribution datasets and consistently observe improved OoD detection performance when evaluating on completely disjoint OoD datasets. Secondly, we perform a transparent post-processing step to discard false positive OoD samples by so-called "meta classification". To this end, we apply linear models to a set of hand-crafted metrics derived from the DNN's softmax probabilities. In our experiments we consistently observe a clear additional gain in OoD detection performance, cutting down the number of detection errors by up to 52 best baseline with our results. We achieve this improvement sacrificing only marginally in original segmentation performance. Therefore, our method contributes to safer DNNs with more reliable overall system performance.

READ FULL TEXT

page 1

page 4

page 13

page 14

page 15

research
03/13/2023

Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentation

In recent years, deep neural networks have defined the state-of-the-art ...
research
11/11/2022

A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Segmentation

Safety-critical applications like autonomous driving use Deep Neural Net...
research
02/17/2022

Detecting and Learning the Unknown in Semantic Segmentation

Semantic segmentation is a crucial component for perception in automated...
research
04/30/2023

Detecting Novelties with Empty Classes

For open world applications, deep neural networks (DNNs) need to be awar...
research
07/13/2022

Automated Detection of Label Errors in Semantic Segmentation Datasets via Deep Learning and Uncertainty Quantification

In this work, we for the first time present a method for detecting label...
research
04/09/2019

Uncertainty Measures and Prediction Quality Rating for the Semantic Segmentation of Nested Multi Resolution Street Scene Images

In the semantic segmentation of street scenes the reliability of the pre...
research
11/12/2019

Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networks

In the semantic segmentation of street scenes, the reliability of a pred...

Please sign up or login with your details

Forgot password? Click here to reset